3 days ago
Sibiu, Romania +2 moreSenior
Responsibilities
- Design end-to-end architectures for Generative AI, agentic AI, enterprise knowledge, document automation, and intelligent workflow solutions.
- Define agent orchestration, tools, APIs, state and memory, retrieval, model routing, human-in-the-loop, observability, and failure-recovery patterns.
- Design enterprise RAG architectures using semantic and hybrid search, vector and graph retrieval, metadata filtering, access controls, citations, reranking, evaluation, and feedback loops.
- Architect foundation-model integration and model gateway patterns covering model selection, routing, fallback, prompt and context management, safety, latency, and cost-performance optimization.
- Design scalable serverless, containerized, API-based, event-driven, hybrid, and on-premises solutions.
- Define security, identity, networking, observability, evaluation, deployment, governance, and LLMOps standards for production AI solutions.
- Build prototypes and reference implementations, review solution designs and code, resolve technical challenges, and provide technical guidance.
- Mentor engineers and contribute to architecture standards, best practices, technology decisions, and client-facing technical consulting.
Requirements
- At least 8 years of relevant experience across software engineering, cloud, data, platform engineering, or AI, including significant enterprise-scale architecture experience.
- Proven experience designing and delivering production AI and machine-learning solutions.
- Hands-on experience delivering production Generative AI and LLM solutions involving RAG, embeddings, retrieval, evaluation, guardrails, and agentic workflows.
- Strong software engineering background with Python and familiarity with Java, C#, TypeScript, JavaScript, Go, or equivalent.
- Strong understanding of REST, gRPC, asynchronous processing, event-driven architectures, and enterprise integration patterns.
- Architecture experience across public cloud, hybrid, private-cloud, and on-premises environments.
- Hands-on experience with AWS AI and application services, including Amazon Bedrock or comparable foundation-model platforms.
- Experience with retrieval architectures using Amazon OpenSearch, PostgreSQL, pgvector, vector databases, and/or graph-based retrieval systems.
- Knowledge of IAM, private networking, secrets management, observability, CI/CD, infrastructure as code, AI evaluation, safety, and production LLMOps.
- Understanding of production AI scalability, reliability, latency, security, governance, and cost optimization.
- Strong client-facing consulting, technical communication, ownership, collaboration, technical decision-making, mentoring, and English-language skills.
- Preferred experience with Amazon Bedrock AgentCore, Bedrock Guardrails, AWS Glue, Lambda, ECS, EKS, LiteLLM, open-source models, model gateways, multi-model architectures, knowledge graphs, graph-based retrieval, Azure AI, regulated or security-sensitive environments, and relevant AWS, Azure, AI, cloud, or architecture certifications.
Tech Stack
Categories
Solutions Engineering
About NTT DATA
NTT DATA is a Tokyo‑headquartered, publicly traded IT services firm within the NTT Group. It provides consulting, application development, system integration, cloud and enterprise application services, and managed/outsourcing services for large enterprises and public-sector organizations. The company operates in more than 50 countries and is listed on the Tokyo Stock Exchange.